softbread avatar

Xiaohongshu Note Analyzer

This analyzer evaluates Xiaohongshu (Little Red Book) posts across six dimensions: keyword optimization, title appeal, sensitive content risks, commercial tone, engagement triggers, and content structure. It checks for banned phrases that could get posts deleted or shadowbanned, scores how promotional your writing sounds (1-10 scale), and suggests viral title formulas like "5 tips that helped me lose 10 pounds." Useful before publishing if you're creating content for Chinese social commerce and want to avoid platform penalties while maximizing reach. The skill outputs a scored report with prioritized fixes, including rewritten versions of your title and opening lines.

skills.sh installs
3.1K
GitHub stars
3
last updated
Jul 14, 2026

Install

$ npx -y skills add softbread/xiaohongshu-doctor --skill xiaohongshu-note-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

小红书笔记分析器 (XiaoHongShu Note Analyzer)

对小红书笔记进行全方位分析,提供优化建议,提升内容质量和曝光率。

分析维度

  1. 关键词分析 — 搜索热度、关键词布局、标签优化
  2. 标题/首段吸引力 — 爆款标题元素、首图文案
  3. 敏感内容风险 — 违规词检测、限流风险评估
  4. 商业化程度 — 软广硬广识别、自然度评分
  5. 互动触发潜力 — 讨论点、分享动机、收藏价值
  6. 内容结构 — 排版、emoji使用、段落节奏

分析流程

1. 提取笔记内容 → 标题、正文、标签、图片描述
2. 关键词分析 → 核心词、长尾词、布局检查
3. 敏感词扫描 → 违规风险、限流风险
4. 商业化评估 → 广告痕迹、自然度
5. 互动潜力评估 → 讨论点、情感共鸣
6. 生成优化建议 → 具体修改方案

1. 关键词分析

检查要点

维度优秀待改进
核心关键词标题+首段+正文+标签都包含仅出现1-2处
长尾关键词3-5个相关长尾词自然分布无长尾词或堆砌
标签数量5-10个相关标签<3个或>15个
关键词密度2-3%自然出现<1%或>5%堆砌

关键词布局公式

标题: 必含核心关键词 + 吸引词
首段(前50字): 核心关键词 + 痛点/好奇点
正文: 长尾关键词自然分布
标签: #核心词 #长尾词 #场景词 #人群词

详见 references/keyword-strategy.md

2. 标题/首段吸引力

爆款标题公式

类型公式示例
数字型数字+关键词+结果"5个技巧让你月瘦10斤"
痛点型痛点+解决方案"毛孔粗大?这个方法亲测有效"
好奇型悬念+关键词"闺蜜问我怎么突然变白的..."
对比型Before/After"用了这个精华,同事都问我怎么了"
权威型身份+干货"皮肤科医生自用的5款防晒"
情绪型强烈情绪词"后悔没早点知道!这个神器太绝了"

首段黄金50字

首段必须包含:

  • ✅ 核心关键词
  • ✅ 痛点/需求点
  • ✅ 吸引继续阅读的钩子
  • ✅ 与封面图呼应

详见 references/title-formulas.md

3. 敏感内容风险评估

风险等级

Sponsors

Details

Repository
github.com/softbread/xiaohongshu-doctor

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs